Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    URLs with common file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    《
    0.46
    ",
    0.44
    <
    0.40
     _
    0.39
     *
    0.39
    VR
    0.38
     @
    0.38
     <
    0.38
     le
    0.38
     ছুর
    0.38
    POSITIVE LOGITS
     Sitemap
    0.48
     semej
    0.47
     Спорттук
    0.47
     Essay
    0.46
    Essay
    0.45
    itemap
    0.43
     essay
    0.42
    шт
    0.41
     semelhantes
    0.41
    рово
    0.41
    Act Density 0.001%

    No Known Activations